Time series and correlation analysis of WHO immunization coverage and disease cases in Nigeria.
# Public Health Data Analysis: Immunization vs. Disease Cases in Nigeria (1974-2018)
**Overview:** This project uses World Health Organization (WHO) data to analyze the temporal trends and correlation between national childhood immunization coverage and the incidence of vaccine-preventable diseases in Nigeria. The primary goal was to quantify the effectiveness of vaccination programs.
## Tools and Technologies
| Category | Tool/Library | Purpose |
| :--- | :--- | :--- |
| **Language** | Python | Core programming language for analysis. |
| **Environment** | Google Colab / Jupyter Notebook | Interactive environment for data cleaning and execution. |
| **Data Manipulation** | Pandas | Loading, cleaning, transformation, and aggregation of data. |
| **Visualization** | Matplotlib, Seaborn | Creating high-quality time-series plots and scatter plots. |
| **Statistics** | Pearson Correlation | Quantifying the strength and direction of the relationship between variables. |
---
## Analysis Questions & Methodology
### Key Questions Addressed:
1. How have the coverage rates for key vaccines (e.g., DTP3, Pol3) trended in Nigeria over time?
2. What are the long-term trends for reported cases of common vaccine-preventable diseases (e.g., Pertussis, Measles)?
### Methodology:
1. **Data Cleaning:** Initial raw data was cleaned by handling metadata rows, selecting relevant columns (`Indicator`, `Year`, `Numeric Value`), and converting the `Year` and `Value` fields to appropriate numeric data types. Missing values were dropped for time-series integrity.
2. **Categorization:** Data was logically separated into two DataFrames: **Immunization Coverage** (percentage-based) and **Disease Cases** (count-based).
3. **Time Series Analysis:** Line plots were generated to visualize long-term trends for the top 5 indicators in each category.
---
## Key Findings
### Time Series Insights:
* **Coverage Success:** Immunization rates for key vaccines like **DTP3** and **Polio (Pol3)* …